论文标题
针对差异隐私的马鞍点会计师
The Saddle-Point Accountant for Differential Privacy
论文作者
论文摘要
我们引入了一个新的差别隐私（DP）会计师，称为鞍点会计师（SPA）。 Spa以准确而快速的方式近似保证DP机制的构成。我们的方法灵感来自鞍点方法 - 统计中普遍存在的数值技术。通过为Spa提供的近似误差，我们通过得出上限和下限来证明性能。水疗中心的关键是与中心极限定理的大型传达方法的组合，我们通过指数倾斜与DP机制相对应的隐私损失随机变量来得出。水疗中心的一个主要优点是，它可以在$ n $折叠机制的$ n $折叠量上持续运行。数值实验表明，水疗中心的准确性与更快的运行时的最新会计方法可比性。
We introduce a new differential privacy (DP) accountant called the saddle-point accountant (SPA). SPA approximates privacy guarantees for the composition of DP mechanisms in an accurate and fast manner. Our approach is inspired by the saddle-point method -- a ubiquitous numerical technique in statistics. We prove rigorous performance guarantees by deriving upper and lower bounds for the approximation error offered by SPA. The crux of SPA is a combination of large-deviation methods with central limit theorems, which we derive via exponentially tilting the privacy loss random variables corresponding to the DP mechanisms. One key advantage of SPA is that it runs in constant time for the $n$-fold composition of a privacy mechanism. Numerical experiments demonstrate that SPA achieves comparable accuracy to state-of-the-art accounting methods with a faster runtime.
